LemonTwoL/ReNeg
ReNeg: Learning Negative Embedding with Reward Guidance
This tool helps improve the visual quality of images and videos generated by AI models like Stable Diffusion. It takes your existing text-to-image or text-to-video prompt and an AI model as input, then generates more visually appealing and higher-quality outputs. Artists, designers, marketers, and content creators who use generative AI for visual content production would find this beneficial.
Use this if you want to enhance the aesthetic quality and visual appeal of AI-generated images and videos from models like Stable Diffusion, Pixart-alpha, ZeroScope, and VideoCrafter2.
Not ideal if you are looking for a tool to generate entirely new images or videos from scratch without improving an existing generative AI workflow.
Stars
35
Forks
—
Language
Python
License
—
Category
Last pushed
Dec 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/LemonTwoL/ReNeg"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
FlorianFuerrutter/genQC
Generative Quantum Circuits
horseee/DeepCache
[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free
Gen-Verse/MMaDA
MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion,...
kuleshov-group/mdlm
[NeurIPS 2024] Simple and Effective Masked Diffusion Language Model
Shark-NLP/DiffuSeq
[ICLR'23] DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models